Miguel Alves Pereira
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Miguel Alves Pereira has a total of 37 co-authors. Here are the top co-authors by number of shared publications:
- Rui Cunha Marques
Universidade Lusófona
9 shared publications - Diogo Cunha Ferreira
CEGIST, Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal
8 shared publications - José Rui Figueira
CEGIST, Instituto Superior Técnico, Universidade de Lisboa, Lisbon, Portugal
5 shared publications - Ana Santos Camanho
Faculdade de Engenharia, Universidade do Porto & INESC TEC
4 shared publications José Rui Figueira
4 shared publications- Giovanna D'INverno
Department of Economics and Management, University of Pisa, Pisa, Italy
3 shared publications
Latest Publications
- Open Access
- 25 July 2026
- Published by Elsevier in SSRN Electronic Journal
Cluster-informed forecasting diagnostics for renewable energy communities:Behavioural segmentation and forecast-error concentration
Renewable Energy Communities (RECs) face persistent forecasting challenges arising from heterogeneous prosumer behaviour, where stable routine-driven consumption coexists with intermittent, high-amplitude demand patterns. Conventional approaches that forecast total community demand as a single aggregate series may obscure how forecast error is distributed across behaviourally distinct groups, limiting the diagnostic value of forecasting outputs for subsequent planning analysis. This study proposes a controlled cluster-informed forecast-diagnostic framework that combines time-series feature engineering, $k$-means clustering, an aggregate-load baseline, a size-matched random-split counterfactual, and a strictly forward-chained rolling-origin protocol. The framework is evaluated on high-resolution smart-meter data from a pilot REC in Aveiro, Portugal, with all segmentation and preprocessing parameters fitted on training data only. Results show that behavioural segmentation yields only marginal gains in aggregate point accuracy (+1.1\%), indicating that high-capacity non-linear models such as XGBoost already capture much of the community-level heterogeneity when trained on total load. The main value of segmentation is diagnostic: regime-level error decomposition reveals a persistent disparity between a regime interpreted as routine-dominated (WAPE 4.93\%) and a regime interpreted as event-driven (WAPE 6.41\%), corresponding to approximately 30\% higher relative forecast error per unit of energy. This asymmetry is invisible under aggregate reporting but becomes analytically accessible through behavioural segmentation. The results demonstrate that controlled behavioural segmentation can add diagnostic information beyond conventional aggregate-load forecasting by indicating where deterministic forecast errors concentrate within a REC.
- 25 July 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessCluster-informed forecasting diagnostics for renewable energy communities:Behavioural segmentation and forecast-error concentration
Renewable Energy Communities (RECs) face persistent forecasting challenges arising from heterogeneous prosumer behaviour, where stable routine-driven consumption coexists with intermittent, high-amplitude demand patterns. Conventional approaches that forecast total community demand as a single aggregate series may obscure how forecast error is distributed across behaviourally distinct groups, limiting the diagnostic value of forecasting outputs for subsequent planning analysis. This study proposes a controlled cluster-informed forecast-diagnostic framework that combines time-series feature engineering, $k$-means clustering, an aggregate-load baseline, a size-matched random-split counterfactual, and a strictly forward-chained rolling-origin protocol. The framework is evaluated on high-resolution smart-meter data from a pilot REC in Aveiro, Portugal, with all segmentation and preprocessing parameters fitted on training data only. Results show that behavioural segmentation yields only marginal gains in aggregate point accuracy (+1.1\%), indicating that high-capacity non-linear models such as XGBoost already capture much of the community-level heterogeneity when trained on total load. The main value of segmentation is diagnostic: regime-level error decomposition reveals a persistent disparity between a regime interpreted as routine-dominated (WAPE 4.93\%) and a regime interpreted as event-driven (WAPE 6.41\%), corresponding to approximately 30\% higher relative forecast error per unit of energy. This asymmetry is invisible under aggregate reporting but becomes analytically accessible through behavioural segmentation. The results demonstrate that controlled behavioural segmentation can add diagnostic information beyond conventional aggregate-load forecasting by indicating where deterministic forecast errors concentrate within a REC.
- Open Access
- 20 April 2026
- Published by Elsevier in SSRN Electronic Journal
Frontier Regulation of Electricity Distribution: Why Economists are Wrong and Engineers are Only Half Right
Frontier benchmarking is central to incentive regulation in electricity distribution. Yet it is typically implemented using nonparametric cost frontiers that impose economic assumptions, such as convexity, thereby abstracting away from sophisticated nonlinear alternating-current power-flow models. This paper shows that, although physically faithful, mathematically accurate specifications of power-flow systems are difficult to deploy for constructing regulatory cost frontiers at scale, while the adoption of nonparametric frontiers can itself give rise to structural misspecifications. We derive a production possibility set and an associated cost function from a stylised power-flow model and compare the resulting engineering benchmark with convex and nonconvex nonparametric estimators. We find that convexification can generate systematic deviations from the engineering cost frontier, whereas nonconvex counterparts provide substantially closer approximations. Evidence from Finnish and Iranian electricity distributors points in the same direction: nonconvex cost frontiers fit the data better and imply materially different efficiency assessments. In this sense, while economists can be wrong in acritically adopting a convex paradigm, engineering models, despite not directly delivering regulatory objects, can be accurately approximated by nonconvex cost frontiers.
- 20 April 2026
- Published by Elsevier in SSRN Electronic Journal
Open AccessFrontier Regulation of Electricity Distribution: Why Economists are Wrong and Engineers are Only Half Right
Frontier benchmarking is central to incentive regulation in electricity distribution. Yet it is typically implemented using nonparametric cost frontiers that impose economic assumptions, such as convexity, thereby abstracting away from sophisticated nonlinear alternating-current power-flow models. This paper shows that, although physically faithful, mathematically accurate specifications of power-flow systems are difficult to deploy for constructing regulatory cost frontiers at scale, while the adoption of nonparametric frontiers can itself give rise to structural misspecifications. We derive a production possibility set and an associated cost function from a stylised power-flow model and compare the resulting engineering benchmark with convex and nonconvex nonparametric estimators. We find that convexification can generate systematic deviations from the engineering cost frontier, whereas nonconvex counterparts provide substantially closer approximations. Evidence from Finnish and Iranian electricity distributors points in the same direction: nonconvex cost frontiers fit the data better and imply materially different efficiency assessments. In this sense, while economists can be wrong in acritically adopting a convex paradigm, engineering models, despite not directly delivering regulatory objects, can be accurately approximated by nonconvex cost frontiers.
- 29 October 2025
- Published by Springer Nature in Health Care Management Science
- Vol. 28 (4) , 824-841
Enhancing clinical and non-clinical risk management: A case study using ELECTRE Tri-nC
Adverse events in healthcare continue to challenge hospital management practices, often resulting in avoidable patient harm and substantial financial costs. Despite technological progress and the availability of risk management tools, healthcare institutions still struggle to systematically monitor and evaluate risk dynamics over time. This study proposes a multi-criteria decision analysis framework based on the ELECTRE Tri-nC method to assess the evolution of clinical and non-clinical risks at Hospital da Luz Lisboa, a private Portuguese hospital. A panel of risk management experts evaluated twelve criteria across five years (2018-2022), enabling the classification of each quarter into one of five predefined risk categories. The model accommodates the non-compensatory nature of risk indicators and integrates expert-defined thresholds. Results reveal critical periods of heightened risk, underscoring the importance of analysing risk trends over time rather than focusing on isolated incidents. A stability analysis confirms the robustness of the weight structure and highlights the model’s sensitivity to changes in the credibility threshold. Overall, the proposed approach provides healthcare decision-makers with a transparent and structured framework for retrospective risk analysis and supports the design of timely, targeted mitigation strategies. The methodology is adaptable to other hospital settings.
- 29 October 2025
- Published by Springer Nature in Health Care Management Science
- Vol. 28 (4) , 824-841
Enhancing clinical and non-clinical risk management: A case study using ELECTRE Tri-nC
Adverse events in healthcare continue to challenge hospital management practices, often resulting in avoidable patient harm and substantial financial costs. Despite technological progress and the availability of risk management tools, healthcare institutions still struggle to systematically monitor and evaluate risk dynamics over time. This study proposes a multi-criteria decision analysis framework based on the ELECTRE Tri-nC method to assess the evolution of clinical and non-clinical risks at Hospital da Luz Lisboa, a private Portuguese hospital. A panel of risk management experts evaluated twelve criteria across five years (2018-2022), enabling the classification of each quarter into one of five predefined risk categories. The model accommodates the non-compensatory nature of risk indicators and integrates expert-defined thresholds. Results reveal critical periods of heightened risk, underscoring the importance of analysing risk trends over time rather than focusing on isolated incidents. A stability analysis confirms the robustness of the weight structure and highlights the model’s sensitivity to changes in the credibility threshold. Overall, the proposed approach provides healthcare decision-makers with a transparent and structured framework for retrospective risk analysis and supports the design of timely, targeted mitigation strategies. The methodology is adaptable to other hospital settings.
- Open Access
A composite indicator framework integrating regulator perspectives for assessing water service quality
- Open Access
Predictive economics: Rethinking economic methodology with machine learning
This article proposes predictive economics as a distinct analytical perspective within economics, grounded in machine learning and centred on predictive accuracy rather than causal identification. Drawing on the instrumentalist tradition (Friedman), the explanation-prediction divide (Shmueli), and the contrast between modelling cultures (Breiman), we formalise prediction as a valid epistemological and methodological objective. Reviewing recent applications across economic subfields, we show how predictive models contribute to empirical analysis, particularly in complex or data-rich contexts. This perspective complements existing approaches and supports a more pluralistic methodology - one that values out-of-sample performance alongside interpretability and theoretical structure.
Open AccessPredictive economics: Rethinking economic methodology with machine learning
This article proposes predictive economics as a distinct analytical perspective within economics, grounded in machine learning and centred on predictive accuracy rather than causal identification. Drawing on the instrumentalist tradition (Friedman), the explanation-prediction divide (Shmueli), and the contrast between modelling cultures (Breiman), we formalise prediction as a valid epistemological and methodological objective. Reviewing recent applications across economic subfields, we show how predictive models contribute to empirical analysis, particularly in complex or data-rich contexts. This perspective complements existing approaches and supports a more pluralistic methodology - one that values out-of-sample performance alongside interpretability and theoretical structure.
- Open Access
- 23 September 2025
- Published by Elsevier in Decision Analytics Journal
- Vol. 17
An integrated approach to hospital efficiency using machine learning and slacks-based super-efficiency evaluation
- 23 September 2025
- Published by Elsevier in Decision Analytics Journal
- Vol. 17
Open AccessAn integrated approach to hospital efficiency using machine learning and slacks-based super-efficiency evaluation
- Open Access
- 20 September 2025
- Published by Wiley in Business Strategy and the Environment
- Vol. 35 (1) , 1097-1111
How Efficient Is the Sustainable Management of Healthcare Supply Chains of the United Nations Member States?
Sustainable practices are essential for the long‐term viability of healthcare systems worldwide, making the study of healthcare supply chains crucial. This research evaluates the efficiency of sustainable healthcare supply chain management across United Nations (UN) Member States by integrating Sustainable Development Goal indicators with network Data Envelopment Analysis (DEA). This methodological approach enables a detailed evaluation of efficiency by decomposing supply chains into interconnected stages, capturing the multidimensional nature of sustainability. Unlike traditional DEA models, network DEA accounts for internal interactions within supply chains, offering precise insights into inefficiencies at specific stages. The study reveals significant variability in supply chain efficiency, independent of human development levels, indicating that lower development indices do not preclude high efficiency when effective policies are implemented. Using data from the UN database, this analysis encompasses economic, environmental and social dimensions, challenging assumptions of a direct correlation between higher human development levels and supply chain efficiency. The findings highlight the importance of context‐specific strategies and provide novel insights into the drivers of efficiency, offering a robust framework for targeted improvements in global healthcare supply chains. The unexpected outperformance of some lower‐developed countries underscores the universal potential to achieve more sustainable and efficient healthcare supply chains.
- 20 September 2025
- Published by Wiley in Business Strategy and the Environment
- Vol. 35 (1) , 1097-1111
Open AccessHow Efficient Is the Sustainable Management of Healthcare Supply Chains of the United Nations Member States?
Sustainable practices are essential for the long‐term viability of healthcare systems worldwide, making the study of healthcare supply chains crucial. This research evaluates the efficiency of sustainable healthcare supply chain management across United Nations (UN) Member States by integrating Sustainable Development Goal indicators with network Data Envelopment Analysis (DEA). This methodological approach enables a detailed evaluation of efficiency by decomposing supply chains into interconnected stages, capturing the multidimensional nature of sustainability. Unlike traditional DEA models, network DEA accounts for internal interactions within supply chains, offering precise insights into inefficiencies at specific stages. The study reveals significant variability in supply chain efficiency, independent of human development levels, indicating that lower development indices do not preclude high efficiency when effective policies are implemented. Using data from the UN database, this analysis encompasses economic, environmental and social dimensions, challenging assumptions of a direct correlation between higher human development levels and supply chain efficiency. The findings highlight the importance of context‐specific strategies and provide novel insights into the drivers of efficiency, offering a robust framework for targeted improvements in global healthcare supply chains. The unexpected outperformance of some lower‐developed countries underscores the universal potential to achieve more sustainable and efficient healthcare supply chains.
- Open Access
- 25 August 2025
- Published by Springer Nature in Annals of Operations Research
- Vol. 353 (3) , 1305-1344
Optimisation of annual payments to public hospitals accounting for quality, access, and efficiency
Since the creation of the Portuguese National Health Service (SNS, from the Portuguese abbreviation of Serviço Nacional de Saúde ), it is the State’s responsibility to ensure the access of the population to quality healthcare, regardless of its economic and social conditions. Efforts for attaining efficiency and reducing wastage, brought along by the successive reforms of the SNS, continue, as the 2009 financial crisis still lingers its effects on the social performance of the provided health services (now again affected by the COVID-19 pandemic). Public hospitals in Portugal are paid following a prospective budget scheme. These contracts define the level of production for each hospital through the computation of unitary costs but do not include variables concerning the access to and quality of health services, which, ultimately, may lead to inefficiencies and misallocation of resources. This study proposes a framework that considers the quality, access, efficiency, and complexity of the Portuguese public hospitals in their payments through the optimisation of the unitary costs established in the contracts, by testing and adapting a ‘best practices payment-based’ tool. Significant cost savings of 64 million € arose for the inpatient service of a relatively small sample of nineteen hospitals, showing high potential for cost containment while aiming for quality, access, and efficiency improvements.
- 25 August 2025
- Published by Springer Nature in Annals of Operations Research
- Vol. 353 (3) , 1305-1344
Open AccessOptimisation of annual payments to public hospitals accounting for quality, access, and efficiency
Since the creation of the Portuguese National Health Service (SNS, from the Portuguese abbreviation of Serviço Nacional de Saúde ), it is the State’s responsibility to ensure the access of the population to quality healthcare, regardless of its economic and social conditions. Efforts for attaining efficiency and reducing wastage, brought along by the successive reforms of the SNS, continue, as the 2009 financial crisis still lingers its effects on the social performance of the provided health services (now again affected by the COVID-19 pandemic). Public hospitals in Portugal are paid following a prospective budget scheme. These contracts define the level of production for each hospital through the computation of unitary costs but do not include variables concerning the access to and quality of health services, which, ultimately, may lead to inefficiencies and misallocation of resources. This study proposes a framework that considers the quality, access, efficiency, and complexity of the Portuguese public hospitals in their payments through the optimisation of the unitary costs established in the contracts, by testing and adapting a ‘best practices payment-based’ tool. Significant cost savings of 64 million € arose for the inpatient service of a relatively small sample of nineteen hospitals, showing high potential for cost containment while aiming for quality, access, and efficiency improvements.
- Open Access
- 23 July 2025
- Published by Elsevier in Decision Analytics Journal
- Vol. 16
An interpretable machine learning framework for explaining company valuation
- 23 July 2025
- Published by Elsevier in Decision Analytics Journal
- Vol. 16
Open AccessAn interpretable machine learning framework for explaining company valuation